CN118233561A - Real-time detection processing method, device, equipment and medium for man-machine conversation jamming - Google Patents

Real-time detection processing method, device, equipment and medium for man-machine conversation jamming Download PDF

Info

Publication number
CN118233561A
CN118233561A CN202410328925.2A CN202410328925A CN118233561A CN 118233561 A CN118233561 A CN 118233561A CN 202410328925 A CN202410328925 A CN 202410328925A CN 118233561 A CN118233561 A CN 118233561A
Authority
CN
China
Prior art keywords
link
real
links
voice stream
acquiring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202410328925.2A
Other languages
Chinese (zh)
Inventor
余文芳
刘宇翔
曾文佳
梁鹏斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lingxi Beijing Technology Co Ltd
Original Assignee
Lingxi Beijing Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Lingxi Beijing Technology Co Ltd filed Critical Lingxi Beijing Technology Co Ltd
Priority to CN202410328925.2A priority Critical patent/CN118233561A/en
Publication of CN118233561A publication Critical patent/CN118233561A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/22—Arrangements for supervision, monitoring or testing
    • H04M3/2236—Quality of speech transmission monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/527—Centralised call answering arrangements not requiring operator intervention

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Robotics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the application provides a real-time detection processing method, device, equipment and medium for man-machine conversation jamming, wherein the method comprises the following steps: acquiring corresponding real-time voice streams of each link in a plurality of links of a conversation scene, wherein the links are a plurality of circulation steps involved in a man-machine conversation process; identifying the corresponding real-time voice stream of each link, and determining the link with abnormal voice stream; and acquiring an abnormality processing step corresponding to the link of the voice stream abnormality, and automatically processing the call stuck abnormality based on the abnormality processing step. According to the method and the device, the links with abnormal voice streams in the links can be found out, so that abnormal processing can be performed on different links, and the abnormal processing efficiency is improved.

Description

Real-time detection processing method, device, equipment and medium for man-machine conversation jamming
Technical Field
The embodiment of the application relates to the field of man-machine conversation, in particular to a real-time detection processing method, device, equipment and medium for man-machine conversation jamming.
Background
In a telephone sales scenario of man-machine communication, in order to achieve cost reduction and efficiency improvement, related technologies generally communicate with users through an AI robot, and when a model predicts that the purchase intention of the users is high, manual work is switched. Therefore, the communication quality in the interaction process of AI and the user becomes an important index for influencing the success and complaint, but the related technology cannot timely find the problems of communication delay, blocking and the like, and can only be checked by a manual spot check mode, but the spot check mode leads to delay of problem finding, thereby reducing the efficiency of abnormality finding and solving.
Therefore, how to improve the efficiency of call abnormality processing becomes a problem to be solved.
Disclosure of Invention
The embodiment of the application provides a real-time detection processing method, device, equipment and medium for man-machine conversation jamming, which can at least find out the links with abnormal voice streams in a plurality of links through some embodiments of the application, so that the abnormal processing can be carried out on different links, and the abnormal processing efficiency is improved.
In a first aspect, the present application provides a method for detecting and processing man-machine conversation stuck in real time, where the method includes: acquiring corresponding real-time voice streams of each link in a plurality of links of a conversation scene, wherein the links are a plurality of circulation steps involved in a man-machine conversation process; identifying the corresponding real-time voice stream of each link, and determining the link with abnormal voice stream; and acquiring an abnormality processing step corresponding to the link of the voice stream abnormality, and automatically processing the call stuck abnormality based on the abnormality processing step.
Therefore, unlike the method for manually checking the call flow in the related art, the embodiment of the application can at least find out the links with abnormal voice flows in a plurality of links by identifying the corresponding real-time voice flows of the links, thereby carrying out abnormal processing on different links and improving the abnormal processing efficiency.
With reference to the first aspect, in an implementation manner of the present application, the identifying the real-time voice stream corresponding to each link and determining the link with abnormal voice stream includes: capturing the corresponding real-time voice stream of each link, and identifying the waveforms in the same period in the capturing to obtain the waveform identification result of each link; and determining the links with abnormal voice flow according to the waveform identification results of the links.
Therefore, the embodiment of the application can rapidly determine the abnormal voice stream in real time by identifying the voice stream of each link, thereby being capable of carrying out targeted processing on the abnormal link.
With reference to the first aspect, in an embodiment of the present application, the step of obtaining an anomaly handling step corresponding to a link of the voice stream anomaly includes: acquiring a storage condition of the robot equipment under the condition that the link of the abnormal voice stream is the robot equipment, wherein the robot equipment is used for automatically carrying out voice interactive communication with a user; and acquiring the corresponding exception processing step according to the storage condition.
Therefore, the embodiment of the application carries out corresponding exception handling through different storage conditions of the robot equipment, and can ensure that the exception handling process is more targeted, thereby improving the exception handling effect.
With reference to the first aspect, in an implementation manner of the present application, the acquiring a storage condition of the robot device includes: acquiring the memory, CPU and disk utilization rate of the robot equipment; the step of obtaining the corresponding exception handling according to the storage condition includes: and under the condition that the memory, the CPU and the disk utilization rate do not meet the preset conditions, acquiring an instruction for restarting the robot equipment.
Therefore, the embodiment of the application can ensure more pertinence in the process of exception handling by carrying out corresponding exception handling on the CPU and the disk utilization rate, thereby improving the effect of exception handling.
With reference to the first aspect, in an implementation manner of the present application, the acquiring the corresponding exception handling step according to the storage case includes: under the condition that the memory, the CPU and the disk utilization rate meet preset conditions, acquiring the memory utilization rate of the browser; and under the condition that the memory utilization rate of the browser meets the preset condition, acquiring an instruction for restarting the browser of the robot equipment.
Therefore, the embodiment of the application can ensure more pertinence in the process of exception handling by carrying out corresponding exception handling on the memory utilization rate of the browser, thereby improving the effect of exception handling.
With reference to the first aspect, in an embodiment of the present application, the plurality of links includes: line link, outbound operating system, robotic device, and AI-dialogue robot.
Therefore, the embodiment of the application can clearly determine the blocked links by carrying out real-time detection of man-machine conversation blocking on a plurality of links, thereby carrying out corresponding exception handling.
In a second aspect, the present application provides a real-time detection processing device for man-machine conversation jamming, where the device includes:
The voice acquisition module is configured to acquire real-time voice streams corresponding to each link in a plurality of links of a conversation scene, wherein the links are a plurality of circulation steps involved in a man-machine conversation process;
The abnormal recognition module is configured to recognize the real-time voice stream corresponding to each link and determine the link with abnormal voice stream;
The abnormality processing module is configured to acquire an abnormality processing step corresponding to the link of the voice stream abnormality and automatically process the call stuck abnormality based on the abnormality processing step.
With reference to the second aspect, in an embodiment of the present application, the anomaly identification module is further configured to: capturing the corresponding real-time voice stream of each link, and identifying the waveforms in the same period in the capturing to obtain the waveform identification result of each link; and determining the links with abnormal voice flow according to the waveform identification results of the links.
With reference to the second aspect, in one embodiment of the present application, the exception handling module is configured to: acquiring a storage condition of the robot equipment under the condition that the link of the abnormal voice stream is the robot equipment, wherein the robot equipment is used for automatically carrying out voice interactive communication with a user; and acquiring the corresponding exception processing step according to the storage condition.
With reference to the second aspect, in one embodiment of the present application, the exception handling module is configured to: acquiring the memory, CPU and disk utilization rate of the robot equipment; and under the condition that the memory, the CPU and the disk utilization rate do not meet the preset conditions, acquiring an instruction for restarting the robot equipment.
With reference to the second aspect, in one embodiment of the present application, the exception handling module is configured to: under the condition that the memory, the CPU and the disk utilization rate meet preset conditions, acquiring the memory utilization rate of the browser; and under the condition that the memory utilization rate of the browser meets the preset condition, acquiring an instruction for restarting the browser of the robot equipment.
With reference to the second aspect, in an embodiment of the present application, the plurality of links includes: line link, outbound operating system, robotic device, and AI-dialogue robot.
In a third aspect, the present application provides an electronic device, comprising: a processor, a memory, and a bus; the processor is connected to the memory via the bus, the memory storing a computer program which, when executed by the processor, performs the method according to any embodiment of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed, performs a method according to any embodiment of the first aspect.
In a fifth aspect, the present application provides a computer program product comprising a computer program/instruction which, when executed, performs a method according to any of the embodiments of the first aspect.
Drawings
Fig. 1 is a processing scenario of real-time detection of man-machine conversation stuck in an embodiment of the present application;
fig. 2 is a flowchart of a processing method for real-time detection of man-machine conversation stuck in an embodiment of the present application;
Fig. 3 is a schematic diagram illustrating a processing device for real-time detection of man-machine conversation stuck in an embodiment of the present application;
fig. 4 is a schematic diagram showing the composition of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without any inventive effort, are intended to be within the scope of the present application based on the embodiments of the present application.
The embodiment of the application can be applied to a scene of monitoring call jamming in real time in the process of man-machine call, and in order to solve the problems in the background technology, in some embodiments of the application, each robot device independently executing robot process automation (Robotic process automation, RPA) acquires corresponding real-time voice streams of each link through monitoring the sound card, converts the voice streams into signals for comparison, and confirms that jamming and delay abnormality occur when the problems such as frame loss occur. Furthermore, because the real-time voice stream passes through the line link, the outbound operating system, the robot equipment and the AI dialogue robot, abnormal links can be automatically found through signal comparison of different links, so that an abnormal processing mode can be distinguished more quickly and accurately, and the abnormal problem can be rapidly and accurately processed.
Therefore, unlike the method for manually checking the call flow in the related art, the embodiment of the application can at least find out the links with abnormal voice flows in a plurality of links by identifying the corresponding real-time voice flows of the links, thereby carrying out abnormal processing on different links and improving the abnormal processing efficiency.
The method steps in the embodiments of the present application are described in detail below with reference to the drawings.
Fig. 1 provides a real-time detection processing scenario of a human-machine conversation card in some embodiments of the present application, which includes a robotic device 110 and a monitoring device 120. The robot device 110 sends the real-time voice stream corresponding to each link to the monitoring device 120, and the monitoring device 120 performs anomaly monitoring and processing after obtaining the real-time voice stream corresponding to each link.
It can be appreciated that the robot device has the function of an agent, and is capable of automatically making a call to a user, interacting with voice, and executing a corresponding automated program. The robotic device needs to be monitored for operation and whether it is operating in the prescribed correct manner.
The following exemplarily illustrates the implementation of a real-time detection processing method for man-machine conversation jamming provided by some embodiments of the present application by using a monitoring device.
At least to solve the problems in the background art, as shown in fig. 2, some embodiments of the present application provide a method for detecting and processing a man-machine conversation card, where the method includes:
s210, acquiring corresponding real-time voice streams of each link in a plurality of links of a call scene.
In one embodiment of the application, before S210, RPA services are independently deployed on a cloud computer, different RPAs are independent of each other, each robot device where the independently operated RPA service is located has a unique IP and a port, an instruction management center of the monitoring device can send instructions to the RPA service through the IP and the port, each robot device is provided with an independent soft-switching solution (FREESWITCH, FS), pulseaudio-module-jack service and an independent sound card, the RPA service is independent of the sound card in the incoming direction through a multi-sound card mode, and data flows in different directions are designated by the service through different sound cards, so that the data do not interfere with each other.
It can be understood that the multiple links of the call scene include multiple circulation steps involved in the human-machine call process, specifically, the multiple links include: line link, outbound operating system, robotic device, and AI-dialogue robot. The plurality of circulation steps are as follows: the user sends out sound to the outbound operating system through the line, then the RPA of the robot equipment acquires a voice stream through the outbound operating system, and finally the voice stream is transmitted to the AI conversation robot.
Where the line is the outbound infrastructure for call use, the line may be provided by a three-party operator. The voice of the line is butted through some protocols and codes to obtain real-time voice stream.
The outbound operating system is a platform for the agent to work on, can manage clients on, and contact clients by making phone calls through the platform, etc.
The AI conversation robot is used to start communicating with the user after the phone is put through.
S220, identifying the corresponding real-time voice stream of each link, and determining the link with abnormal voice stream.
Firstly, capturing a corresponding real-time voice stream of each link, identifying waveforms in the same period in the capturing to obtain waveform identification results of each link, and then determining links with abnormal voice streams according to the waveform identification results of each link.
Specifically, by monitoring the sound card, real-time voice streams of 4 different links are read in real time and stored in a queue. And the voice analysis service takes out the real-time voice stream from the queue, stores the real-time voice stream as a recording (for example, a 5S section) according to a time period, then opens an audio analysis tool by utilizing the RPA service, imports the recording of 4 links, captures the waveform, trend and the like of the same section through the RPA, identifies the capturing by utilizing ocr technology, confirms the recording of inconsistent waveform or trend, finds out the link corresponding to the inconsistent recording according to the corresponding stage of the recording, marks, and finally carries out different automatic processing and replying according to the abnormality appearing in different links. That is, the voice stream can be analyzed in real time through the RPA, abnormal calls and corresponding services can be found in time, and the monitoring equipment distinguishes the links with problems through the analysis of abnormal links, and automatically notifies the abnormal handler.
It can be understood that the RPA may also upload the voice stream to the monitoring device in real time, and the monitoring device performs anomaly recognition and anomaly processing on the voice stream.
In one embodiment of the present application, the stuck anomaly may be classified into silence and frame loss, where the silence analysis mode: the real-time voice stream is read from the sound card, stored as a recording file according to the 3s duration, waveform identification is carried out by utilizing a voice tool and a screenshot ocr, and if the waveform is unchanged or has no fluctuation, the current voice is invalid. And the voices of different links are identified and compared, and the links with problems are judged.
And (3) frame loss analysis mode: the real-time voice stream is read from the sound card, the real-time voice stream is stored as a recording file according to the 3s duration, the waveform recognition is carried out by utilizing a voice tool and a screenshot ocr, all links are compared, links where different audios are located are found out, and the recording is abnormal.
S230, acquiring an abnormality processing step corresponding to the link of the voice stream abnormality, and automatically processing the call stuck abnormality based on the abnormality processing step.
Specifically, in S2301, in the case that the link of the abnormal voice stream is the robot device, the storage condition of the robot device is obtained, where the robot device is used to automatically perform a voice interactive call with the user.
S2302, acquiring corresponding exception processing steps according to the storage condition.
Specifically, the memory, the CPU and the disk utilization rate of the robot device are obtained.
Under one condition, under the condition that the utilization rate of the memory, the CPU and the disk does not meet the preset condition, acquiring an instruction for restarting the robot equipment.
In another case, under the condition that the memory, the CPU and the disk utilization rate meet the preset conditions, the memory utilization rate of the browser is obtained, and then under the condition that the memory utilization rate of the browser meets the preset conditions, an instruction for restarting the browser of the robot device is obtained.
That is, when the analysis finds that frame loss occurs in the robot device, the use rate of the memory, the CPU and the disk of the robot device is obtained through the monitoring service of the monitoring device, and the robot device with the use rate exceeding 85% is restarted by sending an instruction to the robot device through ssh. The instructions are as follows:
shutdown/r/t 0
When the analysis finds that the frame loss occurs in the robot equipment and the utilization rate of server resources (memory, cpu, magnetic disk and the like) is normal, the utilization rate of the memory of the browser is obtained through a python instruction, the robot equipment with the memory occupying more than 80% is sent to the robot equipment through ssh, and the browser is restarted. The instructions are as follows:
taskkill chrome.exe
taskkill chromedriver*
start python XXX.py
When the analysis finds that the frame loss occurs in the AI conversation robot, a command is sent to a server where the FS is located through shh, and the FS is restarted.
Further, when a problem is automatically analyzed to be out of a line link and an outbound operation system, system mails are sent to related responsible persons, meanwhile, the conversation proportion of the problem is counted according to conversation dimension, and when the abnormal proportion exceeds 3% (the threshold value can be customized), the monitoring equipment initiates a request through the api to inform the operation system of locking and stop executing all telephone dialing tasks. If the abnormal proportion is not more than 3%, sending a short message and a mail synchronous related responsible person to manually decide whether to stop the task. When the automatic analysis problem is found in the robot equipment, the memory, CPU and disk utilization rate of the RPA server are obtained, and if the utilization rates exceed the set threshold (such as 85%), an instruction is sent to automatically restart the robot equipment where the RPA is located. If the problem occurs in the robot equipment and the resource utilization rate is normal, the memory utilization rate of the browser is acquired, and if the memory utilization rate exceeds a threshold value, an instruction is sent to automatically restart the browser.
Therefore, the detection coverage is incomplete due to manual spot check in the related art, and the abnormal detection of 100% coverage can be realized through automatic detection of real-time voice flow. In the related art, the judgment standards of quality inspectors cannot be unified, so that the quality of the spot inspection cannot be ensured. In the related art, manual spot inspection can only find problems, but cannot judge the cause of abnormality, and cannot convert the cause into technical terms and technical communication to convey the problems, so that in the process of solving the problems, technicians need to check the problems again.
Therefore, the application can automatically detect the conversation voice quality and cover the whole area; automatically detecting abnormal call, synchronizing related technology, operation and maintenance project responsibility people in real time, providing data basis for timely decision, if more than 5% of call quality is abnormal, stopping line is needed, and avoiding great loss; and the links of abnormal occurrence are automatically analyzed, the problem solving party is distinguished, and the efficiency is improved. If the outbound operation system, the robot equipment and the AI dialogue robot record and the voice flow are normal, but the link of the line is abnormal, the problem of the line side is indicated, the line side should be contacted in time for checking, and the abnormal line is automatically dropped.
The foregoing describes a specific embodiment of a method for detecting and processing man-machine conversation jamming in real time, and the following describes an apparatus for the method for detecting and processing man-machine conversation jamming in real time.
As shown in fig. 3, some embodiments of the present application provide a real-time detection processing apparatus 300 for man-machine conversation jamming, which includes: a speech acquisition module 310, an anomaly identification module 320, and an anomaly handling module 330.
The voice acquisition module 310 is configured to acquire real-time voice streams corresponding to each link in a plurality of links of the conversation scene, wherein the links are a plurality of circulation steps involved in the man-machine conversation process;
The abnormality recognition module 320 is configured to recognize the real-time voice stream corresponding to each link and determine the link with abnormal voice stream;
the exception handling module 330 is configured to obtain an exception handling step corresponding to the link of the voice stream exception, and automatically handle the call stuck exception based on the exception handling step.
In one embodiment of the present application, the anomaly identification module 320 is further configured to: capturing the corresponding real-time voice stream of each link, and identifying the waveforms in the same period in the capturing to obtain the waveform identification result of each link; and determining the links with abnormal voice flow according to the waveform identification results of the links.
In one embodiment of the present application, the exception handling module 330 is configured to: acquiring a storage condition of the robot equipment under the condition that the link of the abnormal voice stream is the robot equipment, wherein the robot equipment is used for automatically carrying out voice interactive communication with a user; and acquiring the corresponding exception processing step according to the storage condition.
In one embodiment of the present application, the exception handling module 330 is configured to: acquiring the memory, CPU and disk utilization rate of the robot equipment; and under the condition that the memory, the CPU and the disk utilization rate do not meet the preset conditions, acquiring an instruction for restarting the robot equipment.
In one embodiment of the present application, the exception handling module 330 is configured to: under the condition that the memory, the CPU and the disk utilization rate meet preset conditions, acquiring the memory utilization rate of the browser; and under the condition that the memory utilization rate of the browser meets the preset condition, acquiring an instruction for restarting the browser of the robot equipment.
In one embodiment of the present application, the plurality of links includes: line link, outbound operating system, robotic device, and AI-dialogue robot.
In an embodiment of the present application, the module shown in fig. 3 is capable of implementing various processes in the embodiments of the methods of fig. 1 and 2. The operation and/or function of the individual modules in fig. 3 are for the purpose of realizing the respective flows in the method embodiments in fig. 1 and 2, respectively. Reference is specifically made to the description in the above method embodiments, and detailed descriptions are omitted here as appropriate to avoid repetition.
As shown in fig. 4, an embodiment of the present application provides an electronic device 400, including: a processor 410, a memory 420 and a bus 430, said processor being connected to said memory by means of said bus, said memory storing computer readable instructions for implementing the method according to any of the above-mentioned embodiments, when said computer readable instructions are executed by said processor, see in particular the description of the above-mentioned method embodiments, and detailed descriptions are omitted here as appropriate for avoiding repetition.
Wherein the bus is used to enable direct connection communication of these components. The processor in the embodiment of the application can be an integrated circuit chip with signal processing capability. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The Memory may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory has stored therein computer readable instructions which, when executed by the processor, perform the method described in the above embodiments.
It will be appreciated that the configuration shown in fig. 4 is illustrative only and may include more or fewer components than shown in fig. 4 or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
Embodiments of the present application also provide a computer readable storage medium, on which a computer program is stored, which when executed by a server, implements a method according to any one of the foregoing embodiments, and specifically reference may be made to the description in the foregoing method embodiments, and detailed descriptions are omitted herein as appropriate for avoiding repetition.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. The real-time detection processing method of man-machine conversation jamming is characterized by comprising the following steps:
Acquiring corresponding real-time voice streams of each link in a plurality of links of a conversation scene, wherein the links are a plurality of circulation steps involved in a man-machine conversation process;
Identifying the corresponding real-time voice stream of each link, and determining the link with abnormal voice stream;
and acquiring an abnormality processing step corresponding to the link of the voice stream abnormality, and automatically processing the call stuck abnormality based on the abnormality processing step.
2. The method of claim 1, wherein the step of identifying the real-time voice stream corresponding to each link and determining the link with abnormal voice stream comprises:
Capturing the corresponding real-time voice stream of each link, and identifying the waveforms in the same period in the capturing to obtain the waveform identification result of each link;
and determining the links with abnormal voice flow according to the waveform identification results of the links.
3. The method according to claim 1 or 2, wherein the step of obtaining an abnormality processing step corresponding to a link of the voice stream abnormality comprises:
acquiring a storage condition of the robot equipment under the condition that the link of the abnormal voice stream is the robot equipment, wherein the robot equipment is used for automatically carrying out voice interactive communication with a user;
And acquiring the corresponding exception processing step according to the storage condition.
4. A method according to claim 3, wherein said retrieving a stored condition of said robotic device comprises:
Acquiring the memory, CPU and disk utilization rate of the robot equipment;
the step of obtaining the corresponding exception handling according to the storage condition includes:
And under the condition that the memory, the CPU and the disk utilization rate do not meet the preset conditions, acquiring an instruction for restarting the robot equipment.
5. The method of claim 4, wherein the step of obtaining the corresponding exception handling according to the storage condition comprises:
under the condition that the memory, the CPU and the disk utilization rate meet preset conditions, acquiring the memory utilization rate of the browser;
And under the condition that the memory utilization rate of the browser meets the preset condition, acquiring an instruction for restarting the browser of the robot equipment.
6. The method of claim 1 or 2, wherein the plurality of links comprises: line link, outbound operating system, robotic device, and AI-dialogue robot.
7. Real-time detection processing apparatus of man-machine conversation card is characterized in that, the device includes:
The voice acquisition module is configured to acquire real-time voice streams corresponding to each link in a plurality of links of a conversation scene, wherein the links are a plurality of circulation steps involved in a man-machine conversation process;
The abnormal recognition module is configured to recognize the real-time voice stream corresponding to each link and determine the link with abnormal voice stream;
The abnormality processing module is configured to acquire an abnormality processing step corresponding to the link of the voice stream abnormality and automatically process the call stuck abnormality based on the abnormality processing step.
8. An electronic device, comprising: a processor, a memory, and a bus;
The processor is connected to the memory via the bus, the memory storing a computer program which, when executed by the processor, performs the method according to any of claims 1-6.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed, implements the method according to any of claims 1-6.
10. A computer program product comprising computer program/instructions which, when executed, implement the method of any of claims 1-6.
CN202410328925.2A 2024-03-21 2024-03-21 Real-time detection processing method, device, equipment and medium for man-machine conversation jamming Pending CN118233561A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410328925.2A CN118233561A (en) 2024-03-21 2024-03-21 Real-time detection processing method, device, equipment and medium for man-machine conversation jamming

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410328925.2A CN118233561A (en) 2024-03-21 2024-03-21 Real-time detection processing method, device, equipment and medium for man-machine conversation jamming

Publications (1)

Publication Number Publication Date
CN118233561A true CN118233561A (en) 2024-06-21

Family

ID=91505327

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410328925.2A Pending CN118233561A (en) 2024-03-21 2024-03-21 Real-time detection processing method, device, equipment and medium for man-machine conversation jamming

Country Status (1)

Country Link
CN (1) CN118233561A (en)

Similar Documents

Publication Publication Date Title
CN107294808B (en) Interface test method, device and system
CN103246735B (en) A kind of method for processing abnormal data and system
CN110501956B (en) Production test alarm system, server and alarm information acquisition equipment
CN112202635B (en) Link monitoring method and device, storage medium and electronic device
CN110231998B (en) Detection method and device for distributed timing task and storage medium
CN113468023A (en) Monitoring method, monitoring device, monitoring medium and electronic equipment
CN111831875A (en) Data processing method, device, equipment and storage medium
US10237408B1 (en) Establishing a target handle time for a communication in a contact center using analytics
CN118233561A (en) Real-time detection processing method, device, equipment and medium for man-machine conversation jamming
WO2021143095A1 (en) Dialing test method and apparatus, and computer device and storage medium
CN105610800A (en) Abnormal data processing method and abnormal data processing apparatus
CN115762514A (en) Intelligent voice quality inspection technology-based electric power business hall abnormal event discovery and handling method and system
CN111934934B (en) Method for realizing remote automatic operation and maintenance through short message transmission
CN107371141B (en) Junk information monitoring method and device and communication system
CN114302398B (en) Big data-based reserved fraud number identification method and device and computing equipment
CN114257688A (en) Telephone fraud identification method and related device
CN114217932A (en) Third-party docking exception handling method and system
CN115396549A (en) Method for processing illegal call service device and electronic apparatus
CN113194026A (en) Message processing method and device
CN114461233A (en) System and method for realizing automatic deployment of data center software based on cloud environment
CN107864057B (en) Online automatic checking and alarming method based on networking state
CN112689112A (en) Time-consuming analysis and optimization method, device, equipment and medium for video communication system
CN111666178A (en) Safety monitoring method and system
CN118113509B (en) System fault detection method
GB2430833A (en) Correlating quality information on different layers of a network model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination